Live Support Chat Widget workflow skill. Use this skill when the user needs Build a real-time support chat system with a floating widget for users and an admin dashboard for support staff. Use when the user wants live chat, customer support chat, real-time messaging, or in-app support and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
Live Support Chat Widget workflow skill. Use this skill when the user needs Build a real-time support chat system with a floating widget for users and an admin dashboard for support staff. Use when the user wants live chat, customer support chat, real-time messaging, or in-app support and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
This public intake copy packages plugins/antigravity-awesome-skills-claude/skills/chat-widget from https://github.com/sickn33/antigravity-awesome-skills into the native Omni Skills editorial shape without hiding its origin.
Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.
This intake keeps the copied upstream files intact and uses the external_source block in metadata.json plus ORIGIN.md as the provenance anchor for review.
Live Support Chat Widget Build a real-time support chat system with a floating widget for users and an admin dashboard for support staff.
Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: Architecture Overview, Implementation Guide, Key Design Decisions, Testing Checklist, Common Pitfalls, Framework-Specific Guidance.
When to Use This Skill
Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.
Add a live chat widget to their app
Build customer support chat functionality
Create real-time messaging between users and admins
Add an in-app support channel
Use when the request clearly matches the imported source intent: Build a real-time support chat system with a floating widget for users and an admin dashboard for support staff. Use when the user wants live chat, customer support chat, real-time messaging, or in-app support.
Use when the operator should preserve upstream workflow detail instead of rewriting the process from scratch.
Operating Table
Situation
Start here
Why it matters
First-time use
metadata.json
Confirms repository, branch, commit, and imported path through the external_source block before touching the copied workflow
Provenance review
ORIGIN.md
Gives reviewers a plain-language audit trail for the imported source
Workflow execution
SKILL.md
Starts with the smallest copied file that materially changes execution
Supporting context
SKILL.md
Adds the next most relevant copied source file without loading the entire package
Handoff decision
## Related Skills
Helps the operator switch to a stronger native skill when the task drifts
Workflow
This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.
Postmark - Best deliverability, simple API
SendGrid - Good free tier, robust
AWS SES - Cheapest at scale
Resend - Modern DX, React email templates
Include message preview (truncated)
Add direct link to open chat (if web app)
Keep subject simple: "New reply from [App] Support"
Imported Workflow Notes
Imported: Email Processing Recommendations
Transactional Email Services
Postmark - Best deliverability, simple API
SendGrid - Good free tier, robust
AWS SES - Cheapest at scale
Resend - Modern DX, React email templates
Implementation Pattern
// Always use background jobs for email
Job: SendSupportReplyNotification
delay: 5 minutes after admin message
perform(message_id):
message = find_message(message_id)
// Guard clauses - don't send if:
if message.sender_type != 'admin': return
if message.read_at != null: return // Already read
if message.chat.archived?: return // Chat archived
send_email(
to: message.chat.user.email,
template: 'support_reply',
data: { message_preview: message.content.truncate(200) }
)
Email Template Tips
Include message preview (truncated)
Add direct link to open chat (if web app)
Keep subject simple: "New reply from [App] Support"
Use @chat-widget to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.
Explanation: This is the safest starting point when the operator needs the imported workflow, but not the entire repository.
Example 2: Ask for a provenance-grounded review
Review @chat-widget against metadata.json and ORIGIN.md, then explain which copied upstream files you would load first and why.
Explanation: Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.
Example 3: Narrow the copied support files before execution
Use @chat-widget for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.
Explanation: This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.
Example 4: Build a reviewer packet
Review @chat-widget using the copied upstream files plus provenance, then summarize any gaps before merge.
Explanation: This is useful when the PR is waiting for human review and you want a repeatable audit packet.
Best Practices
Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.
Keep the imported skill grounded in the upstream repository; do not invent steps that the source material cannot support.
Prefer the smallest useful set of support files so the workflow stays auditable and fast to review.
Keep provenance, source commit, and imported file paths visible in notes and PR descriptions.
Point directly at the copied upstream files that justify the workflow instead of relying on generic review boilerplate.
Treat generated examples as scaffolding; adapt them to the concrete task before execution.
Route to a stronger native skill when architecture, debugging, design, or security concerns become dominant.
Troubleshooting
Problem: The operator skipped the imported context and answered too generically
Symptoms: The result ignores the upstream workflow in plugins/antigravity-awesome-skills-claude/skills/chat-widget, fails to mention provenance, or does not use any copied source files at all.
Solution: Re-open metadata.json, ORIGIN.md, and the most relevant copied upstream files. Check the external_source block first, then restate the provenance before continuing.
Problem: The imported workflow feels incomplete during review
Symptoms: Reviewers can see the generated SKILL.md, but they cannot quickly tell which references, examples, or scripts matter for the current task.
Solution: Point at the exact copied references, examples, scripts, or assets that justify the path you took. If the gap is still real, record it in the PR instead of hiding it.
Problem: The task drifted into a different specialization
Symptoms: The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better.
Solution: Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.
Related Skills
@00-andruia-consultant - Use when the work is better handled by that native specialization after this imported skill establishes context.
@00-andruia-consultant-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.
@10-andruia-skill-smith - Use when the work is better handled by that native specialization after this imported skill establishes context.
@10-andruia-skill-smith-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.
Additional Resources
Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.
Resource family
What it gives the reviewer
Example path
references
copied reference notes, guides, or background material from upstream
references/n/a
examples
worked examples or reusable prompts copied from upstream
examples/n/a
scripts
upstream helper scripts that change execution or validation
scripts/n/a
agents
routing or delegation notes that are genuinely part of the imported package
agents/n/a
assets
supporting assets or schemas copied from the source package
assets/n/a
Imported Reference Notes
Imported: Implementation Guide
Step 1: Data Models
Create two tables: support_chats and support_messages.
support_chats
id - primary key (UUID recommended)
user_id - foreign key to users (UNIQUE - one chat per user)
last_message_at - timestamp (for sorting chats by recency)
admin_viewed_at - timestamp (tracks when admin last viewed)
archived_at - timestamp (null = active, set = archived)
created_at
updated_at
support_messages
id - primary key (UUID recommended)
chat_id - foreign key to support_chats
content - text (required)
sender_type - enum: 'user' | 'admin'
read_at - timestamp (null = unread)
created_at
updated_at
Key indexes:
support_chats.user_id (unique)
support_chats.last_message_at (for sorting)
support_chats.archived_at (for filtering)
support_messages.chat_id
support_messages.(chat_id, created_at) (composite, for ordering)
Model relationships:
User has_one SupportChat
SupportChat belongs_to User
SupportChat has_many SupportMessages
SupportMessage belongs_to SupportChat
Model methods to implement:
Chat model:
function touch_last_message()
update last_message_at = now()
function unread_for_admin?()
return exists message where sender_type = 'user'
and created_at > admin_viewed_at
function mark_viewed_by_admin()
update admin_viewed_at = now()
function archive()
update archived_at = now()
function unarchive()
update archived_at = null
function archived?()
return archived_at != null
Message model:
after_create:
chat.touch_last_message()
if sender_type == 'user' and chat.archived?:
chat.unarchive() // Auto-reactivate on new user message
after_create_commit:
broadcast_to_chat_channel(message_data)
if sender_type == 'user':
broadcast_to_admin_notification_channel(message_data, chat_info)
if sender_type == 'admin':
schedule_email_notification(delay: 5.minutes)
Step 2: API Endpoints
User-facing:
GET /support_chat - Get or create user's chat with messages
PATCH /support_chat/mark_read - Mark admin messages as read
Admin-facing:
GET /admin/chats - List chats (query: archived=true/false)
GET /admin/chats/:id - Get chat with messages
POST /admin/chats/:id/archive - Archive chat
POST /admin/chats/:id/unarchive - Restore chat
Show "You: " prefix if last message was from admin
Chat Detail Page:
Header: user@example.com [Archive/Restore button]
Back link
Messages (grouped by date):
──── Monday, January 29 ────
[User bubble] Message content
10:30 AM
[Admin bubble] Reply content
10:35 AM
Input area (same as widget)
Features:
Group messages by date with dividers
User messages left, admin messages right (opposite of user widget)
Show sender label ("You" for admin, user email/name for user)
Archive/restore toggle button
Same WebSocket subscription as user widget for real-time updates
Call mark_viewed_by_admin() when page loads (server-side)
Step 6: Email Notifications
Send email to user when admin replies and user hasn't seen it.
Job/worker:
class SupportReplyNotificationJob
perform(message):
if message.sender_type != 'admin': return
if message.read_at != null: return // Already read, skip
send_email(
to: message.chat.user.email,
subject: "New reply from Support",
body: "You have a new message from our support team..."
)
Scheduling:
Schedule job with 5-minute delay when admin sends message
This gives user time to see message in-app before email
